Real-Time Monitoring of the Trends of GI Symptoms Searched on the Internet Effectively Predicts the COVID-19 Outbreak

Background: Real-time surveillance of search behavior on the Internet has achieved accessibility in measuring disease activity. Here, we systematically assessed the associations between Internet search trends of GI symptoms and daily newly confirmed COVID-19 cases at the global and country levels. Methods: Relative search volumes (RSVs) of the terms of GI symptoms were derived from Internet search engines. Time-series analyses with autoregressive integrated moving average models were conducted to fit and forecast the RSVs trends of each GI symptom before and after the COVID-19 outbreak. Generalized additive models were used to quantify the effects of RSVs of GI symptoms on the incidence of COVID-19. In addition, dose-response analyses were applied to estimate the shape of the associations. Findings: The RSVs of GI symptoms could be characterized by seasonal variation and high correlation with symptoms of fever and cough at worldwide and country levels; especially, “diarrhea” and “loss of taste” were abnormally increased during the outbreak period of COVID-19 with elevated point changes of 1.31 and 8 times, respectively. In addition, these symptom terms could effectively predict the COVID-19 outbreak in advance underlying lag correlation at 12 and 5 days, respectively, and with mutual independence as well. The dose-response curves showed a consistent increase in daily COVID-19 risk with increasing search volumes of “diarrhea” and “loss of taste”. Interpretation: Our comprehensive research was the first and largest infodemiological study that revealed the advanced prediction of the COVID-19 outbreak via GI symptom indicators. Funding: None to declare. Declaration of Interest: We declare no competing interests.